Presentation Time
00:00
ID: 2427030088

Predictive Vehicle Diagnostics Using Deep Learning

AI-powered proactive engine fault detection using BiLSTM with Attention on OBD-II telemetry, deployed as a production REST API achieving 90.5% fault recall.

Problem Statement

Modern vehicles generate continuous OBD-II telemetry (RPM, temperature, pressure readings) but consumer systems only provide reactive fault codes after failure occurs. There is no accessible, low-cost predictive system capable of detecting abnormal engine behavior before critical failure using standard OBD-II protocols.

πŸ’‘ Key Innovations

πŸ“Š Dataset

πŸ”§ System Architecture

Phase 1: Data Preprocessing
1,699 sequences β€’ 1,200 timesteps β€’ MinMax normalization β€’ Trip-based split
Phase 2: Autoencoder Training
Unsupervised anomaly detection β€’ Validation loss: 0.01095
Phase 3: Reconstruction Labeling
1,334 normal / 365 fault β€’ Zero manual labeling
Phase 4: BiLSTM Classifier
Encoder + Attention + Dense β€’ Binary fault prediction
Phase 5: Threshold Optimization
Grid search (62 thresholds) β€’ F2-optimized: 0.52
Phase 6: Production Deployment
Docker + Flask + Gunicorn β†’ Render.com

πŸ—ΊοΈ Full Pipeline Workflow Diagram

End-to-end pipeline from raw OBD-II telemetry collection through autoencoder-based anomaly labeling, BiLSTM classification, threshold optimization (F2-maximized), and production deployment on Render.com.

Predictive Vehicle Diagnostics Workflow Diagram

Figure 1: Complete 7-Phase Pipeline β€” Data Collection β†’ Preprocessing β†’ Autoencoder β†’ Auto-Labeling β†’ BiLSTM Classifier β†’ Threshold Optimization β†’ Production Deployment

πŸ“ˆ Model Performance

90.5%
Fault Recall
Target: 90%
38.3%
Precision
Test Set
0.52
Threshold
F2 Optimized
0.711
F2 Score
Recall-weighted
<2s
API Response
Production
2.75MB
Model Size
Lightweight
26%
False Alarms
92/354 seqs
1.7%
Missed Faults
6/354 seqs

β€’ Diagnostic Capabilities: 3-tier system (Precise β†’ General β†’ Safety)

β€’ Fault Categories: 8 categories (Sensor, Thermal, Ignition, Throttle, RPM, Electrical)

β€’ Sensor Identification: Attention mechanism highlights critical sensors

β€’ Cost Savings: $225 per test cycle (false alarm reduction)

🌐 Live Deployment

Live & Operational 99.9% Uptime

API Base URL:

https://pbl-predictivevehiclediagnostics.onrender.com

β€’ GET /health β†’ System status & threshold

β€’ POST /predict β†’ Fault probability + diagnostic tier + sensors

β€’ POST /batch_predict β†’ Process multiple sequences

πŸ“– View Documentation


    
Platform: Render.com (Docker container) | Server: Gunicorn (4 workers) | Framework: Flask 3.0

πŸ› οΈ Technology Stack

Machine Learning

TensorFlow 2.10 Keras Scikit-learn NumPy Pandas

Backend

Flask 3.0 Gunicorn 21.2 Python 3.10 Prometheus

Deployment

Docker Render.com GitHub Actions CI/CD

Model Architecture: BiLSTM with Attention Mechanism | Input: (1200, 10) | Output: Binary fault probability

πŸ“‚ Repository

DemWrath/PBL_PredictiveVehicleDiagnostics
classifier.h5 - Trained model (2.75 MB)
deploy_cloud_api.py - Flask API server
diagnostic_engine.py - 3-tier diagnostics
lstm_classifier.py - Model architecture
config.py - Hyperparameters
Dockerfile - Container spec

πŸš€ Future Enhancements

Phase 4.5: Enhanced Diagnostics

  • β€’ 37 specific fault pattern detection (sensor-level)
  • β€’ Physics-based validation rules
  • β€’ Repair cost estimation engine

Phase 7: Real-World Testing

  • β€’ Deploy to test fleet (5-10 vehicles)
  • β€’ Collect production fault data
  • β€’ Retrain with real failure examples

Phase 8: Mobile Application

  • β€’ iOS/Android companion app
  • β€’ Real-time push notifications
  • β€’ OBD-II adapter pairing (Bluetooth)
  • β€’ Maintenance schedule integration

πŸŽ“ Academic Credits

Project Guide

Dr. Neha Janu

Student

Abhinav Jha

ID: 2427030088

Institution

Manipal University Jaipur

Dept. of CSE β€’ 2026

Β© 2026 PBL Project | Predictive Vehicle Diagnostics Using Deep Learning
View Source Code | API Status